Search

Cloud cover is primarily a major difficulty in the acquisition of optical satellite images and has a negative impact on the efficiency of data scheduling. Along with data scheduling, the computational power required is also increasing. Recent advances in an ex-tensive variety of technologies have resulted in an explosion in the amount of data. Different methodologies have been used for Object detection in remote sensing images but it remains a challenge because of its diversity and complex backgrounds. In this paper, a cloud cover detection technique based on Convolutional Neural Networks is proposed for remote sensing images. The classifying model uses a neural network where the underlying features are used to classify the image as useful or not. Results illustrate that the proposed method outperforms other state of the art methods that exist. Once classified, it will be transmitted from the satellite to the earth giving the researchers only convenient pictures to study. This will help to save a massive amount of computation, expense and time. [ABSTRACT FROM AUTHOR]

With the development of Internet technology, short texts have gradually become the main medium for people to obtain information and communicate. Short text reduces the threshold of information production and reading by virtue of its short length, which is in line with the trend of fragmented reading in the context of the current fast-paced life. In addition, short texts contain emojis to make the communication immersive. However, short-text content means it contains relatively little information, which is not conducive to the analysis of sentiment characteristics. Therefore, this paper proposes a sentiment classification method based on the blending of emoticons and short-text content. Emoticons and short-text content are transformed into vectors, and the corresponding word vector and emoticon vector are connected into a sentencing matrix in turn. The sentence matrix is input into a convolution neural network classification model for classification. The results indicate that, compared with existing methods, the proposed method improves the accuracy of analysis. [ABSTRACT FROM AUTHOR]

One of the challenges in the field of remote sensing is how to automatically identify and classify high-resolution remote sensing images. A number of approaches have been proposed. Among them, the methods based on low-level visual features and middle-level visual features have limitations. Therefore, this paper adopts the method of deep learning to classify scenes of high-resolution remote sensing images to learn semantic information. Most of the existing methods of convolutional neural networks are based on the existing model using transfer learning, while there are relatively few articles about designing of new convolutional neural networks based on the existing high-resolution remote sensing image datasets. In this context, this paper proposes a multi-view scaling strategy, a new convolutional neural network based on residual blocks and fusing strategy of pooling layer maps, and uses optimization methods to make the convolutional neural network named RFPNet more robust. Experiments on two benchmark remote sensing image datasets have been conducted. On the UC Merced dataset, the test accuracy, precision, recall, and F1-score all exceed 93%. On the SIRI-WHU dataset, the test accuracy, precision, recall, and F1-score all exceed 91%. Compared with the existing methods, such as the most traditional methods and some deep learning methods for scene classification of high-resolution remote sensing images, the proposed method has higher accuracy and robustness. [ABSTRACT FROM AUTHOR]

Simple Summary: This study investigates the latest achievements, challenges, and future research directions of deep learning techniques for lung cancer and pulmonary nodule detection. Hopefully, these research findings will help scientists, investigators, and clinicians develop new and effective medical imaging tools to improve lung nodule diagnosis accuracy, sensitivity, and specificity. Medical imaging tools are essential in early-stage lung cancer diagnostics and the monitoring of lung cancer during treatment. Various medical imaging modalities, such as chest X-ray, magnetic resonance imaging, positron emission tomography, computed tomography, and molecular imaging techniques, have been extensively studied for lung cancer detection. These techniques have some limitations, including not classifying cancer images automatically, which is unsuitable for patients with other pathologies. It is urgently necessary to develop a sensitive and accurate approach to the early diagnosis of lung cancer. Deep learning is one of the fastest-growing topics in medical imaging, with rapidly emerging applications spanning medical image-based and textural data modalities. With the help of deep learning-based medical imaging tools, clinicians can detect and classify lung nodules more accurately and quickly. This paper presents the recent development of deep learning-based imaging techniques for early lung cancer detection. [ABSTRACT FROM AUTHOR]

Classification of 3D objects – the selection of a category in which each object belongs – is of great interest in the field of machine learning. Numerous researchers use deep neural networks to address this problem, altering the network architecture and representation of the 3D shape used as an input. To investigate the effectiveness of their approaches, we conduct an extensive survey of existing methods and identify common ideas by which we categorize them into a taxonomy. Second, we evaluate 11 selected classification networks on two 3D object datasets, extending the evaluation to a larger dataset on which most of the selected approaches have not been tested yet. For this, we provide a framework for converting shapes from common 3D mesh formats into formats native to each network, and for training and evaluating different classification approaches on this data. Despite being partially unable to reach the accuracies reported in the original papers, we compare the relative performance of the approaches as well as their performance when changing datasets as the only variable to provide valuable insights into performance on different kinds of data. We make our code available to simplify running training experiments with multiple neural networks with different prerequisites. [ABSTRACT FROM AUTHOR]

This paper explores the use of three different two-dimensional time–frequency features for audio event classification with deep neural network back-end classifiers. The evaluations use spectrogram, cochleogram and constant-Q transform-based images for classification of 50 classes of audio events in varying levels of acoustic background noise, revealing interesting performance patterns with respect to noise level, feature image type and classifier. Evidence is obtained that two well-performing features, the spectrogram and cochleogram, make use of information that is potentially complementary in the input features. Feature fusion is thus explored for each pair of features, as well as for all tested features. Results indicate that a fusion of spectrogram and cochleogram information is particularly beneficial, yielding an impressive 50-class accuracy of over 96 % in 0 dB SNR and exceeding 99 % accuracy in 10 dB SNR and above. Meanwhile, the cochleogram image feature is found to perform well in extreme noise cases of - 5 dB and - 10 dB SNR. [ABSTRACT FROM AUTHOR]

In comparison to the competitors, engineers must provide quick, low-cost, and dependable solutions. The advancement of intelligence generated by machines and its application in almost every field has created a need to reduce the human role in image processing while also making time and labor profit. Lepidopterology is the discipline of entomology dedicated to the scientific analysis of caterpillars and the three butterfly superfamilies. Students studying lepidopterology must generally capture butterflies with nets and dissect them to discover the insect's family types and shape. This research work aims to assist science students in correctly recognizing butterflies without harming the insects during their analysis. This paper discusses transfer-learning-based neural network models to identify butterfly species. The datasets are collected from the Kaggle website, which contains 10,035 images of 75 different species of butterflies. From the available dataset, 15 unusual species were selected, including various butterfly orientations, photography angles, butterfly lengths, occlusion, and backdrop complexity. When we analyzed the dataset, we found an imbalanced class distribution among the 15 identified classes, leading to overfitting. The proposed system performs data augmentation to prevent data scarcity and reduce overfitting. The augmented dataset is also used to improve the accuracy of the data models. This research work utilizes transfer learning based on various convolutional neural network architectures such as VGG16, VGG19, MobileNet, Xception, ResNet50, and InceptionV3 to classify the butterfly species into various categories. All the proposed models are evaluated using precision, recall, F-Measure, and accuracy. The investigation findings reveal that the InceptionV3 architecture provides an accuracy of 94.66%, superior to all other architectures. [ABSTRACT FROM AUTHOR]

Three-dimensional (3D) point cloud classification methods based on deep learning have good classification performance; however, they adapt poorly to diverse datasets and their classification accuracy must be improved. Therefore, FSDCNet, a neural network model based on the fusion of static and dynamic convolution, is proposed and applied for multiview 3D point cloud classification in this paper. FSDCNet devises a view selection method with fixed and random viewpoints, which effectively avoids the overfitting caused by the traditional fixed viewpoint. A local feature extraction operator of dynamic and static convolution adaptive weight fusion was designed to improve the model's adaptability to different types of datasets. To address the problems of large parameters and high computational complexity associated with the current methods of dynamic convolution, a lightweight and adaptive dynamic convolution operator was developed. In addition, FSDCNet builds a global attention pooling, integrating the most crucial information on different view features to the greatest extent. Due to these characteristics, FSDCNet is more adaptable, can extract more fine-grained detailed information, and can improve the classification accuracy of point cloud data. The proposed method was applied to the ModelNet40 and Sydney Urban Objects datasets. In these experiments, FSDCNet outperformed its counterparts, achieving state-of-the-art point cloud classification accuracy. For the ModelNet40 dataset, the overall accuracy (OA) and average accuracy (AA) of FSDCNet in a single view reached 93.8% and 91.2%, respectively, which were superior to those values for many other methods using 6 and 12 views. FSDCNet obtained the best results for 6 and 12 views, achieving 94.6%, 93.3%, 95.3%, and 93.6% in OA and AA metrics, respectively. For the Sydney Urban Objects dataset, FSDCNet achieved an OA and F1 score of 81.2% and 80.1% in a single view, respectively, which were higher than most of the compared methods. In 6 and 12 views, FSDCNet reached an OA of 85.3% and 83.6% and an F1 score of 85.5% and 83.7%, respectively. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel training strategy named Feature Mining for convolutional neural networks (CNNs) that aims to strengthen the network's learning of the local features. Through experiments, we found that different parts of the feature contain different semantics, while the network will inevitably lose a large amount of local information during feedforward propagation. In order to enhance the learning of the local features, Feature Mining divides the complete feature into two complementary parts and reuses this divided feature to make the network capture different local information; we call the two steps Feature Segmentation and Feature Reusing. Feature Mining is a parameter-free method with a plug-and-play nature and can be applied to any CNN model. Extensive experiments demonstrated the wide applicability, versatility, and compatibility of our method. [ABSTRACT FROM AUTHOR]

As the number of textual data is exponentially increasing, it becomes more important to develop models to analyze the text data automatically. The texts may contain various labels such as gender, age, country, sentiment, and so forth. Using such labels may bring benefits to some industrial fields, so many studies of text classification have appeared. Recently, the Convolutional Neural Network (CNN) has been adopted for the task of text classification and has shown quite successful results. In this paper, we propose convolutional neural networks for the task of sentiment classification. Through experiments with three well-known datasets, we show that employing consecutive convolutional layers is effective for relatively longer texts, and our networks are better than other state-of-the-art deep learning models. [ABSTRACT FROM AUTHOR]

A reverse vending machine motivates citizens to bring recyclable waste by rewarding them, which is a viable solution to increase the recycling rate. Reverse vending machines generally use near-infrared sensors, barcode sensors, or cameras to classify recycling resources. However, sensor-based reverse vending machines suffer from a high configuration cost and the limited scope of target objects, and conventional single image-based reverse vending machines usually make erroneous predictions about intentional fraud objects. This paper proposes a dual image-based convolutional neural network ensemble model to address these problems. For this purpose, we first created a prototype reverse vending machine and constructed an image dataset containing two cross-sections of objects, top and front view. Then, we chose convolutional neural network models widely used in image classification as the candidates for building an accurate and lightweight ensemble model. Considering the size and classification performance of candidates, we constructed the best-fit ensemble combination and evaluated its classification performance. The final ensemble model showed a classification accuracy higher than 95% for all target classes, including fraud objects. This result proves that our approach achieves better robustness against intentional fraud objects than single image-based models and thus can broaden the scope for target resources. The measurement results on lightweight embedded platforms also demonstrated that our model provides a short inference time that is enough to facilitate the real-time execution of reverse vending machines based on low-cost edge artificial intelligence devices. [ABSTRACT FROM AUTHOR]

Environmental Sound Recognition has become a relevant application for smart cities. Such an application, however, demands the use of trained machine learning classifiers in order to categorize a limited set of audio categories. Although classical machine learning solutions have been proposed in the past, most of the latest solutions that have been proposed toward automated and accurate sound classification are based on a deep learning approach. Deep learning models tend to be large, which can be problematic when considering that sound classifiers often have to be embedded in resource constrained devices. In this paper, a classical machine learning based classifier called MosAIc, and a lighter Convolutional Neural Network model for environmental sound recognition, are proposed to directly compete in terms of accuracy with the latest deep learning solutions. Both approaches are evaluated in an embedded system in order to identify the key parameters when placing such applications on constrained devices. The experimental results show that classical machine learning classifiers can be combined to achieve similar results to deep learning models, and even outperform them in accuracy. The cost, however, is a larger classification time. [ABSTRACT FROM AUTHOR]

In semiconductor manufacturing, a wafer bin map (WBM) represents the results of wafer testing for dies using a binary pass or fail value. For WBMs, defective dies are often clustered into groups of local systematic defects. Determining their specific patterns is important, because different patterns are related to different root causes of failure. Recently, because wafer sizes have increased and the process technology has become more complicated, the probability of observing mixed-type defect patterns, i.e., two or more defect patterns in a single wafer, has increased. In this paper, we propose the use of convolutional neural networks (CNNs) to classify mixed-type defect patterns in WBMs in the framework of an individual classification model for each defect pattern. Through simulated and real data examples, we show that the CNN is robust to random noise and performs effectively, even if there are many random defects in WBMs. [ABSTRACT FROM AUTHOR]

Recurrence-plot (RP) analysis is a graphical tool to visualize and analyze the recurrence of nonlinear dynamic systems. By combining the advantages of the RP and a convolutional neural network (CNN), a fault-classification scheme for planetary gear sets is proposed in this paper. In the proposed approach, a vibration is first picked up from the planetary-gear test rig and converted into an angular-domain quasistationary signal through computed order tracking to eliminate the frequency blur caused by speed fluctuations. Then, the signal in the angular domain is divided into several segments, and each segment is processed by the RP to constitute the training sample. Moreover, a two-dimensional CNN model was developed to adaptively extract faulty features. Experiments on a planetary-gear test rig with four conditions under three operating speeds were carried out. The results of measured vibration demonstrated the validity of CNN and recurrence plot analysis for the fault classification of planetary-gear sets. [ABSTRACT FROM AUTHOR]

In this paper, a Collision Grid Map (CGM) is proposed by using 3d point cloud data to predict the collision between the cattle and the end effector of the manipulator in the barn environment. The Generated Collision Grid Map using x-y plane and depth z data in 3D point cloud data is applied to a Convolutional Neural Network to predict a collision situation. There is an invariant of the permutation problem, which is not efficiently learned in occurring matter of different orders when 3d point cloud data is applied to Convolutional Neural Network. The Collision Grid Map is generated by point cloud data based on the probability method. The Collision Grid Map scheme is composed of a 2-channel. The first channel is constructed by location data in the x-y plane. The second channel is composed of depth data in the z-direction. 3D point cloud is measured in a barn environment and created a Collision Grid Map. Then the generated Collision Grid Map is applied to the Convolutional Neural Network to predict the collision with cattle. The experimental results show that the proposed scheme is reliable and robust in a barn environment. [ABSTRACT FROM AUTHOR]

Customs classification is an essential international procedure to import cross-border goods traded by various companies and individuals. Proper classification of such goods with high efficiency in light of the rapidly increasing amount of international trade is still challenging. The current abundant e-commence data and advanced machine learning techniques provide an opportunity for cross-border e-commerce sellers to classify goods efficiently. Thus, in this paper, we propose a text-image adaptive convolutional neural network to effectively utilize website information and facilitate the customs classification process. The proposed model includes two independent submodels: one for text and the other for image. The submodels are fused by a novel method, which can adjust the value of parameters according to the model training result. Finally, we conduct a case study and comparison experiments based on a group of customs tariff codes and a data set from an e-commerce website. Experiment results indicate the effectiveness of text and image combination in performance improvement, the outperformance of the adaptive fusion method, as well as the potential of this approach when applied to customs classification. [ABSTRACT FROM AUTHOR]

Side-scan sonar is widely used in underwater rescue and the detection of undersea targets, such as shipwrecks, aircraft crashes, etc. Automatic object classification plays an important role in the rescue process to reduce the workload of staff and subjective errors caused by visual fatigue. However, the application of automatic object classification in side-scan sonar images is still lacking, which is due to a lack of datasets and the small number of image samples containing specific target objects. Secondly, the real data of side-scan sonar images are unbalanced. Therefore, a side-scan sonar image classification method based on synthetic data and transfer learning is proposed in this paper. In this method, optical images are used as inputs and the style transfer network is employed to simulate the side-scan sonar image to generate "simulated side-scan sonar images"; meanwhile, a convolutional neural network pre-trained on ImageNet is introduced for classification. In this paper, we experimentally demonstrate that the maximum accuracy of target classification is up to 97.32% by fine-tuning the pre-trained convolutional neural network using a training set incorporating "simulated side-scan sonar images". The results show that the classification accuracy can be effectively improved by combining a pre-trained convolutional neural network and "similar side-scan sonar images". [ABSTRACT FROM AUTHOR]

This study proposes a double-track method for the classification of fruit varieties for application in retail sales. The method uses two nine-layer Convolutional Neural Networks (CNNs) with the same architecture, but different weight matrices. The first network classifies fruits according to images of fruits with a background, and the second network classifies based on images with the ROI (Region Of Interest, a single fruit). The results are aggregated with the proposed values of weights (importance). Consequently, the method returns the predicted class membership with the Certainty Factor (CF). The use of the certainty factor associated with prediction results from the original images and cropped ROIs is the main contribution of this paper. It has been shown that CFs indicate the correctness of the classification result and represent a more reliable measure compared to the probabilities on the CNN outputs. The method is tested with a dataset containing images of six apple varieties. The overall image classification accuracy for this testing dataset is excellent (99.78%). In conclusion, the proposed method is highly successful at recognizing unambiguous, ambiguous, and uncertain classifications, and it can be used in a vision-based sales systems in uncertain conditions and unplanned situations. [ABSTRACT FROM AUTHOR]

This paper constructs a composite classifier based on a convolutional neural network (CNN) and support vector machine (SVM) by using the decision fusion method to study the Wudalianchi Nature Reserve. It also conducts studies on the high-resolution remote sensing image classification of a lake wetland and makes a comparison between the pixel-based SVM method and the context-based CNN method. The experimental results show that the overall accuracy of the SVM-CNN classification method is higher than that of the SVM method, by 9% and 7.75% for the selected two study sites, and higher than the CNN method, by 5.23% and 2.39%. In particular, for the large-area lake wetland, the SVM-CNN classification method provides a higher boundary classification accuracy than the SVM and CNN methods. The research shows that the SVM-CNN composite classifier based on decision fusion theory provides a favorable means for the fine classification of lake wetland identification. [ABSTRACT FROM AUTHOR]

Deep learning techniques based on Convolutional Neural Networks (CNNs) are extensively used for the classification of hyperspectral images. These techniques present high computational cost. In this paper, a GPU (Graphics Processing Unit) implementation of a spatial-spectral supervised classification scheme based on CNNs and applied to remote sensing datasets is presented. In particular, two deep learning libraries, Caffe and CuDNN, are used and compared. In order to achieve an efficient GPU projection, different techniques and optimizations have been applied. The implemented scheme comprises Principal Component Analysis (PCA) to extract the main features, a patch extraction around each pixel to take the spatial information into account, one convolutional layer for processing the spectral information, and fully connected layers to perform the classification. To improve the initial GPU implementation accuracy, a second convolutional layer has been added. High speedups are obtained together with competitive classification accuracies. [ABSTRACT FROM AUTHOR]

The convolutional neural network (CNN)-based pixel-wise synthetic aperture radar (SAR) data classification does not take fully use the spatial neighborhood information due to the fact that the impact of neighborhood pixels is not taken into consideration. The flaw of CNN-based classification method may lead to misclassification under some conditions. In this paper, we propose a novel adaptive neighborhood-based convolutional neural network (AN-CNN) for the single polarimetric synthetic aperture radar data classification. In the convolution layer, the neighborhood pixels are adaptively weighted based on their bilateral distance (spatial and feature distance) to the central pixel. In this way, different pixels have different impact on the classification result of the central pixel. The spatial distance-based weighting can reduce the misclassifications in the homogenous regions which are caused by speckle noise and the feature distance-based weighting is beneficial for the classification in the boundary regions. As a result, the misclassification is obviously reduced by the proposed AN-CNN which has a new cost function. Experimental results on simulated and real SAR data show that our proposed AN-CNN can notably improve the classification accuracy in both boundary regions and homogeneous regions compared with conventional CNN in different scenes especially when limited training samples are explored. [ABSTRACT FROM AUTHOR]

The problem of deep learning network image classification when a large number of image samples are obtained in life and with only a small amount of knowledge annotation, is preliminarily solved in this paper. First, a support vector machine expert labeling system is constructed by using a bag-of-words model to extract image features from a small number of labeled samples. The labels of a large number of unlabeled image samples are automatically annotated by using the constructed SVM expert labeling system. Second, a small number of labeled samples and automatically labeled image samples are combined to form an augmented training set. A deep convolutional neural network model is created by using an augmented training set. Knowledge transfer from SVMs trained with a small number of image samples annotated by artificial knowledge to deep neural network classifiers is implemented in this paper. The problem of overfitting in neural network training with small samples is solved. Finally, the public dataset caltech256 is used for experimental verification and mechanism analysis of the performance of the new method. [ABSTRACT FROM AUTHOR]

Identification of the malignancy of tissues from Histopathological images has always been an issue of concern to doctors and radiologists. This task is time-consuming, tedious and moreover very challenging. Success in finding malignancy from Histopathological images primarily depends on long-term experience, though sometimes experts disagree on their decisions. However, Computer Aided Diagnosis (CAD) techniques help the radiologist to give a second opinion that can increase the reliability of the radiologist's decision. Among the different image analysis techniques, classification of the images has always been a challenging task. Due to the intense complexity of biomedical images, it is always very challenging to provide a reliable decision about an image. The state-of-the-art Convolutional Neural Network (CNN) technique has had great success in natural image classification. Utilizing advanced engineering techniques along with the CNN, in this paper, we have classified a set of Histopathological Breast-Cancer (BC) images utilizing a state-of-the-art CNN model containing a residual block. Conventional CNN operation takes raw images as input and extracts the global features; however, the object oriented local features also contain significant information--for example, the Local Binary Pattern (LBP) represents the effective textural information, Histogram represent the pixel strength distribution, Contourlet Transform (CT) gives much detailed information about the smoothness about the edges, and Discrete Fourier Transform (DFT) derives frequency-domain information from the image. Utilizing these advantages, along with our proposed novel CNN model, we have examined the performance of the novel CNN model as Histopathological image classifier. To do so, we have introduced five cases: (a) Convolutional Neural Network Raw Image (CNN-I); (b) Convolutional Neural Network CT Histogram (CNN-CH); (c) Convolutional Neural Network CT LBP (CNN-CL); (d) Convolutional Neural Network Discrete Fourier Transform (CNN-DF); (e) Convolutional Neural Network Discrete Cosine Transform (CNN-DC). We have performed our experiments on the BreakHis image dataset. The best performance is achieved when we utilize the CNN-CH model on a 200× dataset that provides Accuracy, Sensitivity, False Positive Rate, False Negative Rate, Recall Value, Precision and F-measure of 92.19%, 94.94%, 5.07%, 1.70%, 98.20%, 98.00% and 98.00%, respectively. [ABSTRACT FROM AUTHOR]

Adopting a deep learning model into bird sound classification tasks becomes a common practice in order to construct a robust automated bird sound detection system. In this paper, we employ a four-layer Convolutional Neural Network (CNN) formulated to classify different species of Indonesia scops owls based on their vocal sounds. Two widely used representations of an acoustic signal: log-scaled mel-spectrogram and Mel Frequency Cepstral Coefficient (MFCC) are extracted from each sound file and fed into the network separately to compare the model performance with different inputs. A more complex CNN that can simultaneously process the two extracted acoustic representations is proposed to provide a direct comparison with the baseline model. The dual-input network is the well-performing model in our experiment that achieves 97.55% Mean Average Precision (MAP). Meanwhile, the baseline model achieves a MAP score of 94.36% for the mel-spectrogram input and 96.08% for the MFCC input. [ABSTRACT FROM AUTHOR]

This paper investigates the performance of a Deep Convolutional Neural Network (DCNN) algorithm to identify bleeding areas of wireless capsule endoscopy (WCE) images without known prior knowledge of bleeding and normal features of the images. In this study, a pre-processing technique has been proposed to improve the classification accuracy of WCE images into bleeding areas and normal areas by enhancing the WCE images. The proposed technique is applied to WCE images from six cases and divided into one training case and five test cases. To evaluate the effectiveness of the processes, the results were then compared between DCNN, SVM and Fuzzy, and also between DCNN with completely enhanced images and DCNN with normalized images. DCNN has shown to give a better result compared to SVM and Fuzzy logic; and the latter experiment has shown that the WCE images that have undergone the proposed enhancement technique gives better classification result compared to those images that did not go through the technique. The specificity, sensitivity and average are 0.8703, 0.8271 and 0.8907 respectively. In conclusion, DCNN has been proven to be able to successfully detecting bleeding areas from images without having any specific knowledge on imaging diagnosis or pathology. [ABSTRACT FROM AUTHOR]

In the financial business, there are cumbersome and error-prone manual procedures and long workflows. In this paper, MSCNN model is proposed to solve automatically identify and classify images such as documents. First, the image data is preprocessed to enhance the image features. Then, the image is extracted by the cross-connect structure and multi-channel convolution. Finally, the image is classified by softmax layer. The experimental results on the dataset show that the proposed model has a high classification accuracy in image classification. [ABSTRACT FROM AUTHOR]

Diabetic retinopathy (DR) is an illness occurring in the eye due to increase in blood glucose level. Among people in the age group of 70, 50% of deaths are attributed to diabetes. Early identification and appropriate treatment can reduce the loss of sight in many DR patients. Once the symptoms of DR are recognized, the severity of the disease should be evaluated for administering the right medication. This paper focuses on the classification of DR fundus images according to the severity of the disease using convolutional neural network with the application of suitable Pooling, Softmax and Rectified Linear Activation Unit (ReLU) layers to obtain a high level of accuracy. The performance of the proposed algorithm has been validated using Messidor database. In the case of healthy images, images of stage1, stage 2 and stage 3 of diabetic retinopathy, classification accuracies of 96.6% and 96.2%, 95.6% and 96.6% have been achieved. [ABSTRACT FROM AUTHOR]

The Faster Region-based Convolutional Network (Faster R-CNN) was recently proposed achieving outstanding performance for object detection. Specially, a Region Proposal Network (RPN) is designed to efficiently predict region proposals with a wide range of scales and aspect ratios in Faster R-CNN. Nevertheless, once the number and quality of region proposals generated by RPN are not ideal the object detection performance of Faster R-CNN is affected. In this paper, multiple strategies are applied to address these limitations and improve RPN. Hence, a novel architecture for region proposal generation is presented which is named as Multi-strategy Region Proposal Network (MSRPN). Four improvements are presented in MSRPN. Firstly, a novel skip-layer connection network is designed for combining multi-level features and boosting the ability of pooling layers. Thereupon, the quality of region proposals is strengthened. Secondly, improved anchor boxes are introduced with adaptive aspect ratio and evenly distributed interval of selected scales. In this way, the number of predicted region proposals for detection is seriously reduced and the efficiency of object localization is increased. Particularly, the capability of small object detection is enhanced by applying the first and second improvements. Thirdly, classification layer and regression layer are unified as a single convolutional layer. Furthermore, the model complexity of output layer is reduced. Thus, the speed of training and testing is accelerated. Fourthly, the bounding box regression part of multi-task loss function in RPN is improved. Consequently, the performance of bounding box regression is promoted. In the experiment, MSRPN is compared with the Fast Region-based Convolutional Network (Fast R-CNN), Faster R-CNN, Inside-Outside Net (ION), Multi-region CNN (MR-CNN) and HyperNet approaches. MSRPN achieves the state-of-the-art mean average precision (mAP) of 78.9%, 74.8% and 32.1% on PASCAL VOC 2007, 2012 and MS COCO data sets with the deep VGG-16 model, surpassing other five object detection methods. Simultaneously, the above experiment results are obtained by MSRPN with only 150 region proposals per image. Additionally, MSRPN gets excellent performance on small object detection. Furthermore, MSRPN runs at 6 fps which is faster than other methods. In conclusion, the MSRPN method can provide important support for the intelligent object detection systems. [ABSTRACT FROM AUTHOR]

Assistive devices for disabled people with the help of Brain-Computer Interaction (BCI) technology are becoming vital bio-medical engineering. People with physical disabilities need some assistive devices to perform their daily tasks. In these devices, higher latency factors need to be addressed appropriately. Therefore, the main goal of this research is to implement a real-time BCI architecture with minimum latency for command actuation. The proposed architecture is capable to communicate between different modules of the system by adopting an automotive, intelligent data processing and classification approach. Neuro-sky mind wave device has been used to transfer the data to our implemented server for command propulsion. Think-Net Convolutional Neural Network (TN-CNN) architecture has been proposed to recognize the brain signals and classify them into six primary mental states for data classification. Data collection and processing are the responsibility of the central integrated server for system load minimization. Testing of implemented architecture and deep learning model shows excellent results. The proposed system integrity level was the minimum data loss and the accurate commands processing mechanism. The training and testing results are 99% and 93% for custom model implementation based on TN-CNN. The proposed real-time architecture is capable of intelligent data processing unit with fewer errors, and it will benefit assistive devices working on the local server and cloud server. [ABSTRACT FROM AUTHOR]

Recently, convolutional neural network (CNN) has achieved impressive results in object classification tasks. Through various modifications and careful design of the inner structure of CNN, its performance has already become human-competitive, according to recent reports. To some extent, the testing accuracy depends largely on the decision boundaries produced by classifiers, which classify different objects into specific feature spaces. Hence, the relationships among samples in the feature space are critical. However, the softmax loss function that is used in most CNN models, does not directly contain the relationship information. In this paper, we propose a novel loss function, named inter-class constraint loss function, that maximizes the distance between different classes. Together with softmax loss, we can obtain larger inter-class distances and smaller intra-class distances in CNN, thus significantly improving the accuracy in classification. We achieve substantial improvements for the SVHN, CIFAR-10 and CIFAR-100 datasets using our proposed loss function. [ABSTRACT FROM AUTHOR]

Deep convolutional neural networks (DCNNs) have shown significant improvements in remote sensing image scene classification for powerful feature representations. However, because of the high variance and volume limitations of the available remote sensing datasets, DCNNs are prone to overfit the data used for their training. To address this problem, this paper proposes a novel scene classification framework based on a deep Siamese convolutional network with rotation invariance regularization. Specifically, we design a data augmentation strategy for the Siamese model to learn a rotation invariance DCNN model that is achieved by directly enforcing the labels of the training samples before and after rotating to be mapped close to each other. In addition to the cross-entropy cost function for the traditional CNN models, we impose a rotation invariance regularization constraint on the objective function of our proposed model. The experimental results obtained using three publicly-available scene classification datasets show that the proposed method can generally improve the classification performance by 2~3% and achieves satisfactory classification performance compared with some state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Changes in the retina of the eyes may occur due to high blood pressure, hypertensive retinopathy (HR) is a type of eye disease in which there is a change of the blood vessels of the eyes in the eye retina caused by arterial hypertension. HR signs occur because of narrowing of the arteries in the retina, bleeding in the retina of the eye and cotton wool spots. The diagnosis is conventionally performed by an ophthalmologist by performing fundus image analysis to determine the phases of HR disease symptoms. This paper proposes an early detection system of hypertensive retinopathy disease. We propose to use Fundus image as a Convolutional Neural Network (CNN) input to determine whether there are any HR symptoms or not. The proposed system is tested by DRIVE image dataset and base on experiment, the accuracy of proposed method is 98.6%, where the more the number of iterations the higher the accuracy level of the training [ABSTRACT FROM AUTHOR]

Recently, deep learning has been reported to be an effective method for improving hyperspectral image classification and convolutional neural networks (CNNs) are, in particular, gaining more and more attention in this field. CNNs provide automatic approaches that can learn more abstract features of hyperspectral images from spectral, spatial, or spectral-spatial domains. However, CNN applications are focused on learning features directly from image data—while the intrinsic relations between original features, which may provide more information for classification, are not fully considered. In order to make full use of the relations between hyperspectral features and to explore more objective features for improving classification accuracy, we proposed feature relations map learning (FRML) in this paper. FRML can automatically enhance the separability of different objects in an image, using a segmented feature relations map (SFRM) that reflects the relations between spectral features through a normalized difference index (NDI), and it can then learn new features from SFRM using a CNN-based feature extractor. Finally, based on these features, a classifier was designed for the classification. With FRML, our experimental results from four popular hyperspectral datasets indicate that the proposed method can achieve more representative and objective features to improve classification accuracy, outperforming classifications using the comparative methods. [ABSTRACT FROM AUTHOR]

Deep learning has attracted extensive attention in the field of hyperspectral images (HSIs) classification. However, supervised deep learning methods heavily rely on a large amount of label information. To address this problem, in this paper, we propose a two-stage deep domain adaptation method for hyperspectral image classification, which can minimize the data shift between two domains and learn a more discriminative deep embedding space with very few labeled target samples. A deep embedding space is first learned by minimizing the distance between the source domain and the target domain based on Maximum Mean Discrepancy (MMD) criterion. The Spatial–Spectral Siamese Network is then exploited to reduce the data shift and learn a more discriminative deep embedding space by minimizing the distance between samples from different domains but the same class label and maximizes the distance between samples from different domains and class labels based on pairwise loss. For the classification task, the softmax layer is replaced with a linear support vector machine, in which learning minimizes a margin-based loss instead of the cross-entropy loss. The experimental results on two sets of hyperspectral remote sensing images show that the proposed method can outperform several state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Deep learning has achieved great success in hyperspectral image classification. However, when processing new hyperspectral images, the existing deep learning models must be retrained from scratch with sufficient samples, which is inefficient and undesirable in practical tasks. This paper aims to explore how to accurately classify new hyperspectral images with only a few labeled samples, i.e., the hyperspectral images few-shot classification. Specifically, we design a new deep classification model based on relational network and train it with the idea of meta-learning. Firstly, the feature learning module and the relation learning module of the model can make full use of the spatial–spectral information in hyperspectral images and carry out relation learning by comparing the similarity between samples. Secondly, the task-based learning strategy can enable the model to continuously enhance its ability to learn how to learn with a large number of tasks randomly generated from different data sets. Benefitting from the above two points, the proposed method has excellent generalization ability and can obtain satisfactory classification results with only a few labeled samples. In order to verify the performance of the proposed method, experiments were carried out on three public data sets. The results indicate that the proposed method can achieve better classification results than the traditional semisupervised support vector machine and semisupervised deep learning models. [ABSTRACT FROM AUTHOR]

Land-cover information is significant for land-use planning, urban management, and environment monitoring. This paper presented a novel extended topology-preserving segmentation (ETPS)-based multi-scale and multi-feature method using the convolutional neural network (EMMCNN) for high spatial resolution (HSR) image land-cover classification. The EMMCNN first segmented the images into superpixels using the ETPS algorithm with false-color composition and enhancement and built parallel convolutional neural networks (CNNs) with dense connections for superpixel multi-scale deep feature learning. Then, the multi-resolution segmentation (MRS) object hand-delineated features were extracted and mapped to superpixels for complementary multi-segmentation and multi-type representation. Finally, a hybrid network was designed to consist of 1-dimension CNN and multi-layer perception (MLP) with channel-wise stacking and attention-based weighting for adaptive feature fusion and comprehensive classification. Experimental results on four real HSR GaoFen-2 datasets demonstrated the superiority of the proposed EMMCNN over several well-known classification methods in terms of accuracy and consistency, with overall accuracy averagely improved by 1.74% to 19.35% for testing images and 1.06% to 8.78% for validating images. It was found that the solution combining an appropriate number of larger scales and multi-type features is recommended for better performance. Efficient superpixel segmentation, networks with strong learning ability, optimized multi-scale and multi-feature solution, and adaptive attention-based feature fusion were key points for improving HSR image land-cover classification in this study. [ABSTRACT FROM AUTHOR]

This paper proposes a framework to perform the sensor classification by using multivariate time series sensors data as inputs. The framework encodes multivariate time series data into two-dimensional colored images, and concatenate the images into one bigger image for classification through a Convolutional Neural Network (ConvNet). This study applied three transformation methods to encode time series into images: Gramian Angular Summation Field (GASF), Gramian Angular Difference Field (GADF), and Markov Transition Field (MTF). Two open multivariate datasets were used to evaluate the impact of using different transformation methods, the sequences of concatenating images, and the complexity of ConvNet architectures on classification accuracy. The results show that the selection of transformation methods and the sequence of concatenation do not affect the prediction outcome significantly. Surprisingly, the simple structure of ConvNet is sufficient enough for classification as it performed equally well with the complex structure of VGGNet. The results were also compared with other classification methods and found that the proposed framework outperformed other methods in terms of classification accuracy. [ABSTRACT FROM AUTHOR]

Background: The Gleason grading system is an important clinical practice for diagnosing prostate cancer in pathology images. However, this analysis results in significant variability among pathologists, hence creating possible negative clinical impacts. Artificial intelligence methods can be an important support for the pathologist, improving Gleason grade classifications. Consequently, our purpose is to construct and evaluate the potential of a Convolutional Neural Network (CNN) to classify Gleason patterns. Methods: The methodology included 6982 image patches with cancer, extracted from radical prostatectomy specimens previously analyzed by an expert uropathologist. A CNN was constructed to accurately classify the corresponding Gleason. The evaluation was carried out by computing the corresponding 3 classes confusion matrix; thus, calculating the percentage of precision, sensitivity, and specificity, as well as the overall accuracy. Additionally, k-fold three-way cross-validation was performed to enhance evaluation, allowing better interpretation and avoiding possible bias. Results: The overall accuracy reached 98% for the training and validation stage, and 94% for the test phase. Considering the test samples, the true positive ratio between pathologist and computer method was 85%, 93%, and 96% for specific Gleason patterns. Finally, precision, sensitivity, and specificity reached values up to 97%. Conclusion: The CNN model presented and evaluated has shown high accuracy for specifically pattern neighbors and critical Gleason patterns. The outcomes are in line and complement others in the literature. The promising results surpassed current inter-pathologist congruence in classical reports, evidencing the potential of this novel technology in daily clinical aspects. [ABSTRACT FROM AUTHOR]

Transfer learning can enhance classification performance of a target domain with insufficient training data by utilizing knowledge relating to the target domain from source domain. Nowadays, it is common to see two or more source domains available for knowledge transfer, which can improve performance of learning tasks in the target domain. However, the classification performance of the target domain decreases due to mismatching of probability distribution. Recent studies have shown that deep learning can build deep structures by extracting more effective features to resist the mismatching. In this paper, we propose a new multi-source deep transfer neural network algorithm, MultiDTNN, based on convolutional neural network and multi-source transfer learning. In MultiDTNN, joint probability distribution adaptation (JPDA) is used for reducing the mismatching between source and target domains to enhance features transferability of the source domain in deep neural networks. Then, the convolutional neural network is trained by utilizing the datasets of each source and target domain to obtain a set of classifiers. Finally, the designed selection strategy selects classifier with the smallest classification error on the target domain from the set to assemble the MultiDTNN framework. The effectiveness of the proposed MultiDTNN is verified by comparing it with other state-of-the-art deep transfer learning on three datasets. [ABSTRACT FROM AUTHOR]

Text sentiment analysis is an important but challenging task. Remarkable success has been achieved along with the wide application of deep learning methods, but deep learning methods dealing with text sentiment classification tasks cannot fully exploit sentiment linguistic knowledge, which hinders the development of text sentiment analysis. In this paper, we propose a sentiment-feature-enhanced deep neural network (SDNN) to address the problem by integrating sentiment linguistic knowledge into a deep neural network via a sentiment attention mechanism. Specifically, first we introduce a novel sentiment attention mechanism to help select the crucial sentiment-word-relevant context words by leveraging the sentiment lexicon in an attention mechanism, which bridges the gap between traditional sentiment linguistic knowledge and current popular deep learning methods. Second, we develop an improved deep neural network to extract sequential correlation information and text local features by combining bidirectional gated recurrent units with a convolutional neural network, which further enhances the ability of comprehensive text representation learning. With this design, the SDNN model can generate a powerful semantic representation of text to improve the performance of text sentiment classification tasks. Extensive experiments were conducted to evaluate the effectiveness of the proposed SDNN model on two real-world datasets with a binary-sentiment-label and a multi-sentiment-label. The experimental results demonstrated that the SDNN achieved substantially better performance than the strong competitors for text sentiment classification tasks. [ABSTRACT FROM AUTHOR]

Accurate segmentation of leukocytes is a primary and very difficult problem because of the non-uniform color, uneven illumination of blood smear image. An improved algorithm based on feature weight adaptive K-means clustering for extracting complex leukocytes is proposed. In this paper, the initial clustering center is chosen according to the histogram distribution of a cell image; this approach not only improves the clustering effect but also reduces the time complexity of the algorithm from O (n) to O (1). Prior to white blood cell extraction, the color space is decomposed. Then, color space decomposition and K-means clustering are combined for image segmentation. And then adherent complex white blood cells are separated again based on watershed algorithm. Finally, classification experiments based on convolutional neural network were performed and compared with other methods; 368 representative images were used to evaluate the performance of our method. The proposed segmentation method achieves 95.81% segmentation accuracy. The classification accuracy reached a maximum of 98.96%, and the average classification time is 0.39 s. Compared with those in the existing algorithms for WBC, convolutional neural network classification method not only presents obvious advantages but can also be easily improved. [ABSTRACT FROM AUTHOR]

Various classification methods have been developed to extract meaningful information from Airborne Laser Scanner (ALS) point clouds. However, the accuracy and the computational efficiency of the existing methods need to be improved, especially for the analysis of large datasets (e.g., at regional or national levels). In this paper, we present a novel deep learning approach to ground classification for Digital Terrain Model (DTM) extraction as well as for multi-class land-cover classification, delivering highly accurate classification results in a computationally efficient manner. Considering the top–down acquisition angle of ALS data, the point cloud is initially projected on the horizontal plane and converted into a multi-dimensional image. Then, classification techniques based on Fully Convolutional Networks (FCN) with dilated kernels are designed to perform pixel-wise image classification. Finally, labels are transferred from pixels to the original ALS points. We also designed a Multi-Scale FCN (MS-FCN) architecture to minimize the loss of information during the point-to-image conversion. In the ground classification experiment, we compared our method to a Convolutional Neural Network (CNN)-based method and LAStools software. We obtained a lower total error on both the International Society for Photogrammetry and Remote Sensing (ISPRS) filter test benchmark dataset and AHN-3 dataset in the Netherlands. In the multi-class classification experiment, our method resulted in higher precision and recall values compared to the traditional machine learning technique using Random Forest (RF); it accurately detected small buildings. The FCN achieved precision and recall values of 0.93 and 0.94 when RF obtained 0.91 and 0.92, respectively. Moreover, our strategy significantly improved the computational efficiency of state-of-the-art CNN-based methods, reducing the point-to-image conversion time from 47 h to 36 min in our experiments on the ISPRS filter test dataset. Misclassification errors remained in situations that were not included in the training dataset, such as large buildings and bridges, or contained noisy measurements. [ABSTRACT FROM AUTHOR]

Accurate knowledge of crop type information is not only valuable for verifying the declaration of farmers to obtain subsidy or insurance for the grown crop, but also for generating crop type maps that serve a variety of purposes in land monitoring and policy. On the other hand, accurate knowledge of crop phenological stage can help farm personnel apply fertilization and irrigation regimes on a timely basis. Although deep learning based networks have been applied in the past to classify the type and predict the phenological stage of crops from in situ images of fields, more advanced deep learning based networks, that learn and make such inferences from temporal windows of sequences of field images taken by cameras at stationary coordinates and looking directions, have not been reported to date. This work proposes a conceivable architecture for learning and making inferences from such data. Specifically, the feature vectors of the images in a temporal window of the image sequence for a crop cycle are extracted by a first stage deep convolutional neural network and their temporal dependencies are exploited by a second stage recurrent neural network. Experiments on a dataset of image sequences from 63 fields of 5 different types of crops reveal that the proposed system can achieve over 80% accuracy in crop type classification and under 0.5 mean absolute error in phenological stage number estimation. The learning performances improve with the size of the temporal window and the fine-tuning of the deep convolutional neural network used for feature extraction. The performances achieved with the proposed system are superior to those obtained by applying classical machine learning methods to handcrafted texture and color features. [ABSTRACT FROM AUTHOR]

Background: A limitation of traditional differential expression analysis on small datasets involves the possibility of false positives and false negatives due to sample variation. Considering the recent advances in deep learning (DL) based models, we wanted to expand the state-of-the-art in disease biomarker prediction from RNA-seq data using DL. However, application of DL to RNA-seq data is challenging due to absence of appropriate labels and smaller sample size as compared to number of genes. Deep learning coupled with transfer learning can improve prediction performance on novel data by incorporating patterns learned from other related data. With the emergence of new disease datasets, biomarker prediction would be facilitated by having a generalized model that can transfer the knowledge of trained feature maps to the new dataset. To the best of our knowledge, there is no Convolutional Neural Network (CNN)-based model coupled with transfer learning to predict the significant upregulating (UR) and downregulating (DR) genes from both trained and untrained datasets. Results: We implemented a CNN model, DEGnext, to predict UR and DR genes from gene expression data obtained from The Cancer Genome Atlas database. DEGnext uses biologically validated data along with logarithmic fold change values to classify differentially expressed genes (DEGs) as UR and DR genes. We applied transfer learning to our model to leverage the knowledge of trained feature maps to untrained cancer datasets. DEGnext's results were competitive (ROC scores between 88 and 99 % ) with those of five traditional machine learning methods: Decision Tree, K-Nearest Neighbors, Random Forest, Support Vector Machine, and XGBoost. DEGnext was robust and effective in terms of transferring learned feature maps to facilitate classification of unseen datasets. Additionally, we validated that the predicted DEGs from DEGnext were mapped to significant Gene Ontology terms and pathways related to cancer. Conclusions: DEGnext can classify DEGs into UR and DR genes from RNA-seq cancer datasets with high performance. This type of analysis, using biologically relevant fine-tuning data, may aid in the exploration of potential biomarkers and can be adapted for other disease datasets. [ABSTRACT FROM AUTHOR]

Intelligent fault diagnosis can be related to applications of machine learning theories to machine fault diagnosis. Although there is a large number of successful examples, there is a gap in the optimization of the hyper-parameters of the machine learning model, which ultimately has a major impact on the performance of the model. Machine learning experts are required to configure a set of hyper-parameter values manually. This work presents a convolutional neural network based data-driven intelligent fault diagnosis technique for rotary machinery which uses model with optimized hyper-parameters and network structure. The proposed technique input raw three axes accelerometer signal as high definition 1-D data into deep learning layers with optimized hyper-parameters. Input is consisted of wide 12,800 × 1 × 3 vibration signal matrix. Model learning phase includes Bayesian optimization that optimizes hyper-parameters of the convolutional neural network. Finally, by using a Convolutional Neural Network (CNN) model with optimized hyper-parameters, classification in one of the 8 different machine states and 2 rotational speeds can be performed. This study accomplished the effective classification of different rotary machinery states in different rotational speeds using optimized convolutional artificial neural network for classification of raw three axis accelerometer signal input. Overall classification accuracy of 99.94% on evaluation set is obtained with the CNN model based on 19 layers. Additionally, more data are collected on the same machine with altered bearings to test the model for overfitting. Result of classification accuracy of 100% on second evaluation set has been achieved, proving the potential of using the proposed technique. [ABSTRACT FROM AUTHOR]

• A new model for acoustic scene classification is proposed. • A relationship between time-frequency resolution and receptive field is modeled. • A fine-resolution feature with semantic information is used for classification. • The proposed method can customize feature representations in various resolutions. • Compared to other deep CNNs, the proposed model reduces computational complexity. Convolutional neural networks with spectrogram feature representation for acoustic scene classification are attracting more and more attentions due to its favorable performance. However, most of the existing methods are still restricted to the tradeoff between the minimum coverage area across time-frequency feature representation, i.e. time-frequency feature resolution, and the depth of CNN models. Thus, it is unfeasible to improve the performance by simply deepening networks. In this paper, fine-resolution convolutional neural network (FRCNN) is proposed to embrace the progress in very deep architecture, feature fusion and convolutional operation. Specifically, lateral construction is applied to generate a fine-resolution feature map with semantic information, and depth-wise separable convolution is utilized to reduce the number of trainable parameters. Extensive experiments demonstrate that the proposed FRCNN exhibits high performance on several metrics, with low computational complexity. [ABSTRACT FROM AUTHOR]

This work presents convolutional neural network (CNN) based methodology for electroencephalogram (EEG) classification by diagnosis: benign childhood epilepsy with centro- temporal spikes (rolandic epilepsy) (Group I) and structural focal epilepsy (Group II). Manual classification of these groups is sometimes difficult, especially, when no clinical record is available, thus presenting a need for an algorithm for automatic classification. The presented algorithm has the following steps: (i) EEG spike detection by morphological filter based algorithm; (ii) classification of EEG spikes using preprocessed EEG signal data from all channels in the vicinity of the spike detected; (iii) majority rule classifier application to all EEG spikes from a single patient. Classification based on majority rule allows us to achieve 80% average accuracy (despite the fact that from a single spike one would obtain only 58% accuracy). [ABSTRACT FROM AUTHOR]

The identification of DNA sequences as exon and intron is a common problem in genome analysis. The methods used for feature extraction and mapping techniques for the digitization of sequences affect directly the solution of this problem. The existing mapping techniques are not enough to detect coding and noncoding regions in some genomes because the digital representation of each base in a DNA sequence with an integer does not fully reflect the structure of an original DNA sequence. In the entropy-based mapping technique, we could overcome this problem because the technique deepens distinction rates of exon regions, and better reflects the complexity of DNA sequences. Moreover, in the literature, features are extracted by using various statistical techniques. The statistical features to be extracted are chosen by a system designer's experience. The other proposed approach in this study is to carry out the feature extraction using the transfer learning method. Transfer learning and feature extraction are performed automatically by convolutional neural network models as independent of the data set. In this study, we propose a new method to classify DNA sequences as exon and intron using two approaches. In the first approach, the entropy-based numerical technique was used for the numerical representation of DNA sequences. In the second approach, transfer learning was used to extract features. Then, the obtained features were classified by support vector machine and k -nearest neighbors algorithm. As a result of the classification, accurate performance with 97.8% was achieved. The performance of the current method was compared with the other numerical mapping techniques and feature extraction methods. The results showed that the developed method was much more successful than other methods. [ABSTRACT FROM AUTHOR]

Huge amount of time series data over several domains such as engineering, biomedical and finance, demands the development of efficient methods for the problem of time series classification. The classification of univariate and multivariate time series together using a single architecture is a very difficult task. In this work, a bio-inspired convolutional spiking neural network (CSNN) is proposed for both univariate and multivariate time series. For this, first we develop a simple transformation to convert raw time series sequences into matrices. The CSNN is a three staged framework which include convolutional feature extraction, spike encoding using soft leaky integrate and fire (Soft-LIf) and classification. As spikes generated are differentiable, thus the learning algorithm for CSNN uses error-backpropagation with cyclical learning rates (CLR) and RMSprop optimizer. Additionally, validation based stopping rules are employed to overcome the overfitting which also provides a set of parameters associated with low validation set loss. Thereafter, to demonstrate the accuracy and robustness of proposed CSNN model, we have used University of California (UCR) univariate as well as University of East Anglia (UEA) multivariate datasets to perform the experiments. Moreover, we conduct comparative empirical performance evaluation with benchmark methods and also with recent deep networks proposed for time series classification. Our results reveal that proposed CSNN advances the baseline methods by achieving higher performance accuracy for both univariate and multivariate datasets. It is shown that the CLR with RMSprop optimizer is able to achieve faster convergence, however CLR and adaptive rates are considered competitive to each other. In addition, we also address the optimal model selection and study the effects of different factors on the performance of proposed CSNN. [ABSTRACT FROM AUTHOR]

Background: Enhancers are non-coding DNA fragments which are crucial in gene regulation (e.g. transcription and translation). Having high locational variation and free scattering in 98% of non-encoding genomes, enhancer identification is, therefore, more complicated than other genetic factors. To address this biological issue, several in silico studies have been done to identify and classify enhancer sequences among a myriad of DNA sequences using computational advances. Although recent studies have come up with improved performance, shortfalls in these learning models still remain. To overcome limitations of existing learning models, we introduce iEnhancer-ECNN, an efficient prediction framework using one-hot encoding and k-mers for data transformation and ensembles of convolutional neural networks for model construction, to identify enhancers and classify their strength. The benchmark dataset from Liu et al.'s study was used to develop and evaluate the ensemble models. A comparative analysis between iEnhancer-ECNN and existing state-of-the-art methods was done to fairly assess the model performance. Results: Our experimental results demonstrates that iEnhancer-ECNN has better performance compared to other state-of-the-art methods using the same dataset. The accuracy of the ensemble model for enhancer identification (layer 1) and enhancer classification (layer 2) are 0.769 and 0.678, respectively. Compared to other related studies, improvements in the Area Under the Receiver Operating Characteristic Curve (AUC), sensitivity, and Matthews's correlation coefficient (MCC) of our models are remarkable, especially for the model of layer 2 with about 11.0%, 46.5%, and 65.0%, respectively. Conclusions: iEnhancer-ECNN outperforms other previously proposed methods with significant improvement in most of the evaluation metrics. Strong growths in the MCC of both layers are highly meaningful in assuring the stability of our models. [ABSTRACT FROM AUTHOR]